diff --git a/collector/utils/extensions/YoutubeTranscript/YoutubeLoader/youtube-transcript.js b/collector/utils/extensions/YoutubeTranscript/YoutubeLoader/youtube-transcript.js index c81c0ec565cc7befdae333b616ffac975cb13f8b..f868875b264e3f20fe970ad7c57dbecfb5e3b68a 100644 --- a/collector/utils/extensions/YoutubeTranscript/YoutubeLoader/youtube-transcript.js +++ b/collector/utils/extensions/YoutubeTranscript/YoutubeLoader/youtube-transcript.js @@ -47,10 +47,12 @@ class YoutubeTranscript { let transcript = ""; const chunks = transcriptXML.getElementsByTagName("text"); for (const chunk of chunks) { - transcript += chunk.textContent; + // Add space after each text chunk + transcript += chunk.textContent + " "; } - return transcript; + // Trim extra whitespace + return transcript.trim().replace(/\s+/g, " "); } catch (e) { throw new YoutubeTranscriptError(e); }